Expedient and Monotone Learning Rules
نویسندگان
چکیده
This paper considers learning rules for environments in which little prior and feedback information is available to the decision maker. Two properties of such learning rules are studied: absolute expediency and monotonicity. Both require that some aspect of the decision maker’s performance improves from the current period to the next. The paper provides some necessary, and some sufficient conditions for these properties. It turns out that there is a large variety of learning rules that have the properties. However, all learning rules that have these properties are related to the replicator dynamics of evolutionary game theory. For the case in which there are only two actions, it is shown that one of the absolutely expedient learning rules dominates all others.
منابع مشابه
A note on absolutely expedient learning rules
I provide a full characterization of the set of absolutely expedient learning rules introduced in Börgers, Morales, and Sarin (2004) [“Expedient and monotone learning rules,” Econometrica, 72, 383–405]. The expected change in the expected payoff can be written as a quadratic form on the vector of relative expected payoffs of the strategies. This permits use of standard linear algebra arguments ...
متن کاملSome results on $L$-complete lattices
The paper deals with special types of $L$-ordered sets, $L$-fuzzy complete lattices, and fuzzy directed complete posets.First, a theorem for constructing monotone maps is proved, a characterization for monotone maps on an $L$-fuzzy complete lattice is obtained, and it's proved that if $f$ is a monotone map on an $L$-fuzzy complete lattice $(P;e)$, then the least fixpoint of $f$ is meet of a spe...
متن کاملMinimax Rules Under Zero-One Loss for a Restricted Location
Minimax Rules Under Zero-One Loss In this paper, we obtain minimax and near-minimax nonrandomized decision rules under zeroone loss for a restricted location parameter of an absolutely continuous distribution. Two types of rules are addressed: monotone and nonmonotone. A complete-class theorem is proved for the monotone case. This theorem extends the previous work of Zeytinoglu and Mintz (1984)...
متن کاملAlmost Equalizer, Bayes and Minimax Decision Rules
In this report minimax and near-minimax nonrandomized decision rules under zero-one loss for a restricted location parameter of an absolutely continuous distribution are obtained. Two types of rules are addressed: monotone and non-monotone. A complete-class theorem is obtained in the monotone case, where the results are an extension of a previous work of Zeytinoglu and Mintz (1984) from the cas...
متن کاملA Hybrid Machine Translation System Based on a Monotone Decoder
In this paper, a hybrid Machine Translation (MT) system is proposed by combining the result of a rule-based machine translation (RBMT) system with a statistical approach. The RBMT uses a set of linguistic rules for translation, which leads to better translation results in terms of word ordering and syntactic structure. On the other hand, SMT works better in lexical choice. Therefore, in our sys...
متن کامل